Downloads · 30 days
0
yolor_w6
kadirnar/yolor_w6
yolor_w6 is a object detection model from kadirnar. Use it when you need objects located in an image. It is set up for yolor. The card lists the license as gpl-3.0.
YOLOR: You Only Learn One Representation: Unified Network for Multiple Tasks.
Access
Public
Updated Jan 16, 2023
Repo size
693 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt320 MB · 100%
At a glance
- Task
- Object Detection
- Library
- yolor
- License
- gpl-3.0
- Access
- Public
- Created
- Jan 15, 2023
- Updated
- Jan 16, 2023
- SHA
- 050e65aa
Datasets
Model card
From the Hugging Face model README
Model Description
YOLOR: You Only Learn One Representation: Unified Network for Multiple Tasks.
YOLOR-Pip: Packaged version of the YOLOR repository
Paper Repo: Implementation of paper - YOLOR
Installation
pip install yolor
Yolov6 Inference
from yolor.helpers import Yolor
model = Yolor(
cfg='yolor/cfg/yolor_w6.cfg',
weights='kadirnar/yolor-w6',
imgsz=640,
device='cuda:0'
)
model.classes = None
model.conf = 0.25
model.iou_ = 0.45
model.show = False
model.save = True
model.predict('yolor/data/highway.jpg')
BibTeX Entry and Citation Info
@article{wang2021you,
title={You Only Learn One Representation: Unified Network for Multiple Tasks},
author={Wang, Chien-Yao and Yeh, I-Hau and Liao, Hong-Yuan Mark},
journal={arXiv preprint arXiv:2105.04206},
year={2021}
}
- Task
- Object Detection
- Library
- yolor
- License
- gpl-3.0
- Languages
- en
- Created
- Jan 15, 2023
- Updated
- Jan 16, 2023